Spectral Clustering Using Friendship Path Similarity

As an important task in machine learning and computer vision, the clustering analysis has been well studied and solved using different approaches such as k-means, Spectral Clustering, Support Vector Machine, and Maximum Margin Clustering. Some of these approaches are specific solutions to the Graph Clustering problem which needs a similarity measure between samples to create the graph. We propose a novel similarity matrix based on human being perception which introduces information of the dataset density and geodesic connections, with the interesting property of parameter independence. We have tested the novel approach in some synthetic as well as real world datasets giving a better average performance in relation to the current state of the art.